• Korean Journal of Ichthyology
• /
• v.24 no.3
• /
• pp.167-176
• /
• 2012

In comparison of the body color of Zacco platypys from Korea, it was found that there were significant differences among geographical populations in the color of upper eye, snout tip and anterior margin of pectoral fin. In individuals with red upper eye the snout tip was red but in those with black upper eye red color did not appeared on the snout tip. There was no difference between male and female in this characteristic and it was expressed uniformly within the same population. So we divided Z. platypus into two types by the color of upper eye; R type with red upper eye and B type with black upper eye. Red band on anterior margin of pectoral fins appeared in all males of both R and B type populations but in females it appeared only in B type individuals. The two types shown different distribution pattern in Korean Peninsula. R type distributed in almost whole area but B type distributed only in southeastern part of the peninsula: Nakdong, Hyeongsan, Taehwa, Suyeong and Jinjeon River. In analysis of external morphology among two types of Z. platypus from Korea and Z. platypus from Japan, there were no significant differences. But they were relatively well separated in discriminant function analysis.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.35-44
• /
• 2010

In this paper, we propose a method about producing skin color model adaptively in input image and face detection. The principle process which we proposed is finding eyes candidates by applying the eye features to neural network, and then using the around color to find the distribution of color value. There will be a verification process that producing face region by using color value distribution which is detected as skin region and find mouth candidate in corresponding face region; if eye candidate and mouth candidate's connection structure is similar with face structure, then it can be judged as a face. Because this method can detect skin region adaptively by finding eyes, we solve the rate of false positive about the distorted skin color which is used by existing face detection methods. The experiment was performed about detecting the eye, the skin, the mouth and the face individually. The results revealed that the proposed technique is better than the traditional techniques.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.82-89
• /
• 2015

The researches of image recognition have been processed traditionally. Especially, face recognition technology has been received attractions with advance and applied to various areas according as camera sensor embedded into many devices such as smart phone. In this study, we design and develop a feature vector generation technique of face for making animation caricatures using methods for face detection which are previous stage of face recognition. At first, we detect both face region and detailed eye region of component element by Viola&Johns's realtime detection method which are called as ROI(Region Of Interest). And then, we generate feature vectors of eye region by utilizing factors as opposed to the periphery and by using appearance information of eye. At this point, we focus on the embedded information in many color spaces to overcome the problems which can be occurred by using one color space. We propose a feature vector generation method using information from many color spaces. Finally, we experiment the test of feature vector generation by the proposed method with enough quantity of sample picture data and evaluate the proposed method for factors of estimating performance such as error rate, accuracy and generation time.

• Journal of the Institute of Convergence Signal Processing
• /
• v.1 no.1
• /
• pp.42-48
• /
• 2000

In this paper, we propose the face image recognition algorithm using skin color information, face region features such as eye, nose, and mouse, etc., and geometrical features of chin line. In the proposed algorithm, we used the intensity as well as skin color information in the HSI color coordinate which is similar to human eye system. The experimental results of proposed method shows improved extraction quality of face and provides adaptive extraction methods for the races. And also, we used chin line information as well as geometrical features of face such as eye, nose, mouse information for the improvement of face recognition quality, Experimental results shows the more improved recognition as well as extraction quality than conventional methods.

• Genomics & Informatics
• /
• v.11 no.2
• /
• pp.93-96
• /
• 2013

The prediction of externally visible characteristics from DNA has been studied for forensic genetics over the last few years. Externally visible characteristics include hair, skin, and eye color, height, and facial morphology, which have high heritability. Recent studies using genome-wide association analysis have identified genes and variations that correlate with human visible phenotypes and developed phenotype prediction programs. However, most prediction models were constructed and validated based on genotype and phenotype information on Europeans. Therefore, we need to validate prediction models in diverse ethnic populations. In this study, we selected potentially useful variations for forensic science that are associated with hair and eye color, iris pattern, and facial morphology, based on previous studies, and analyzed their frequencies in 1,920 Koreans. Among 20 single nucleotide polymorphisms (SNPs), 10 SNPs were polymorphic, 6 SNPs were very rare (minor allele frequency < 0.005), and 4 SNPs were monomorphic in the Korean population. Even though the usability of these SNPs should be verified by an association study in Koreans, this study provides 10 potential SNP markers for forensic science for externally visible characteristics in the Korean population.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2006.11a
• /
• pp.168-172
• /
• 2006

With the progress of the aging society into the aged society, the planning of senior housing is inevitably required. Among the factors of planning, color appeals to people's vision which mostly accepts information about the environment, so age-related color vision changes should be studied. The purpose of the study is to find out characteristics of color perception focused on yellow and blue with advancing of the yellowed eye sight in the old age. The findings are as follows. (1) Regardless of gender, losses of color perception in sensitivity is occurred as aging is proceeded. But the rate of reduction is mitigated compared with the ex-research in Japan because of the promotion of physical health. (2) Human lens coloration was not common until 85 years old and the hue of yellow and red was easily perceived by the older subjects. (3) Yellow is more preferred to other colors by the elderly and accuracy of yellow-color perception is higher than that of blue-color. (4) It is especially hard for the elderly to perceive the difference between pure blue and mixture of blue-green. Therefore blue and blue-green should not be adopted simultaneously in senior housing environment. Except for the space which specially requires carefulness, various color preferred by the elderly should be applied to the senior housing environment to satisfy their psychological condition and provide the vitality of life.

• Publications of The Korean Astronomical Society
• /
• v.30 no.2
• /
• pp.761-763
• /
• 2015

Colors have been derived from the observed optical spectrum of Mars and Jupiter. It is known that the planets and the Moon emit reflected sunlight and thus their spectra are similar to the spectrum of solar radiation. The question was then why is the color of Mars different from that of other planets, i.e. red, although it would share the same spectrum of reflected sunlight. Can one derive color from the spectrum? Therefore, we observed the optical spectra of the scattered sunlight in day time for the Moon and Mars using a 1-D array spectrograph on the 12-inch reflecting telescope in the Korea Science Academy of KAIST in Busan, Korea. We adopted the International Commission on Illumination (CIE) in 1931 of three spectral sensitivity peaks for the human eye in short, medium and long wavelengths in visible light. The observed spectra were imposed on CIE sensitivities and the color detected by the human eye was derived. The Mars spectrum represents red color and the Moon white. It is a similar color to that which a human would see. This result means that color is easily derived from astronomical spectra. The appearance of the planets surface can be determined for Mars, which is the result of iron oxide.

• Journal of Fashion Business
• /
• v.9 no.2
• /
• pp.20-27
• /
• 2005

To find suitable color for an individual is very important in personal image-making. In recent years, the importance and role of personal image is also more emphasized. This study deals with the necessity d personal color system and the proposal of color which looks nice on a person as a result d personal color system. It also includes the method of making personal image by balancing between and using both favorite color and unfavorite color. Besides, I study how does the color image affect the personal appearance image in this paper. From clinical experiments, I concluded as follow. First, Each person has his suitable color. When the color is used, the color, pimples, flows and so on are covered and defects of his face are made up for. Second, By changing the factors of his own original color-group and decision factors - color d skin, hair, eye, etc -, I can change personal color-group. Third, The image of color affects the personal appearance image, when it used in make-up and hair-color. Considering above results, If one uses one's suitable color, one will complement defects done's face and improve merits of one's. Besides, One will be more confident and active by using one's suitable color.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.531-535
• /
• 1999

Automatic human face detection in a complex background is one of the difficult problems. In this paper, we propose an effective and robust automatic face detection approach that can locate the face region in natural scene images when the system is used as a pre-processor of a face recognition system . We use two natural and powerful visual cues, the skin color and the eyes. In the first step of the proposed system, the method based on the human skin color space by selecting flesh tone regions using normalized r-g space in color images. In the next step, we extract eye features by calculating moments and using geometrical face model. Experimental results demonstrate that the approach can efficiently detect human faces and satisfactory deal with the problems caused by bad lighting condition, skew face orientation.

• Journal of the Korean Society of Fashion and Beauty
• /
• v.1 no.1 s.1
• /
• pp.27-47
• /
• 2003

This research is to build the foundation of systematic application of color in cosmetology by analyzing color attributes in women's makeup presentation. The result were as follows. 1. The most popular color series in make up were R then RP and YR. The most popular color tone is 'd' and 'lt'. 2. Colors in make up according to age was as follows. For eye shadow, people aged 18 to 24 used 'lt' tone of the R color series; people aged 25 to 34 used 'lt', 's', 'sf tone of the R color series, 'lt' tone of the PB color series, 'lt' tone of the YR color series; people over 35 'g' tone of the YR color series, 'sf' tone of the P color series. For lipstick, people aged 18 to 24 used 'd' tone of the R color series; people aged 25 to 34 used 'd', 'sf' tone of the R color series; people over 35 used 'd' tone of the R color series. For lip-gloss, people aged 18 to 24 used 'v', 'lt', 'b', 's' tone of the R color series; people aged 25 to 34 used 's' 'd' 'dp' 'sf' tone of the R color series; people over 35 used 'b' tone of the R color series. 3. Make up colors according to marital status was as follows. For eye shadow, while married interviewees used 's', 'dk' tone of the R color series, single interviewees used 'lt', 'sf' tone of the R color series. For lipstick, while married interviewees used 'd', 'g' tone of the R color series, single interviewees preferred to use madder 'd', 'sf' tone of the R color series. For lip-gross, while married interviewees used 'd' tone of the R color series, single interviewees used 'b' tone of the R color series the most.